1. 16 Apr, 2010 7 commits
  2. 15 Apr, 2010 26 commits
  3. 14 Apr, 2010 7 commits
    • Jonathon Duerig's avatar
    • Jonathon Duerig's avatar
      Added disk image support to ptopgen and a set of 0.2 schema files which allow... · 98517b23
      Jonathon Duerig authored
      Added disk image support to ptopgen and a set of 0.2 schema files which allow disk images in the rspec..
      98517b23
    • Mike Hibler's avatar
      Reduce from 3 DB queries per node to 1 total query. · e4173cfa
      Mike Hibler authored
      Reduce the running time by 50%...from 1 second to 0.5 seconds.
      A marvel of pointless optimization!  At the time it seemed like it might
      matter, but the case that is really slow (requiring a call to nalloc per
      node) is still slow.  But it was a twenty minute diversion.
      e4173cfa
    • Mike Hibler's avatar
      Merge remote branch 'central/master' · a4abf46f
      Mike Hibler authored
      a4abf46f
    • Mike Hibler's avatar
      Add some useful elabinelab sitevars. · 9bb38c10
      Mike Hibler authored
      New sitevars:
        elabinelab/singlenet     set the system-wide default for cnet implementation
        elabinelab/boss_osid     default OSID for boss node
        elabinelab/ops_osid      default OSID for ops node
        elabinelab/fs_osid       default OSID for fs node
      
      Also mark the various elabinelab/*pkg* sitevars as deprecated.  Package
      versions are just too dependent on the OS running and we almost always
      wind up overriding these sitevars in rc.mkelab anyway.
      9bb38c10
    • Mike Hibler's avatar
      36d218a5
    • Mike Hibler's avatar
      Changes for speeding up elabinelab server setup. · 6feda7d3
      Mike Hibler authored
      Boss/ops/fs: reboot them together after setup rather than serially.
      
      Nodes: leave them in PXEWAIT throughout the setup, until after boss has
      been rebooted.  At that point we send them the new bootinfo RESTART command
      telling pxeboot to re-DHCP and use the new info obtained (next-server) to
      contact a potentially new boss node.  This is a quick way to switch a node
      in PXEWAIT from talking to the outer boss to talking to the inner one.
      
      A significant number of rinky-dink changes were needed to do this, primarily
      adding a new state, PXELIMBO, where nodes can be sent to sit until they are
      restarted.  It turns out, just putting them in an existing state such as
      PXEWAKEUP or SHUTDOWN wouldn't work, as they tend to timeout or otherwise
      reboot.
      6feda7d3